search

cnnlstm / FSLSD_HiRes

104 stars 10 forks source link

test on FF++ #7

Open tyrink opened 2 years ago

tyrink commented 2 years ago

Hi, have you tested your released model on FF++? I follewed all your preprocessing steps, but the synthetic inner face is about a mess. However, following the same steps, I got proper synthetic faces on CelebAHQ dataset. I really wonder what's wrong with FF++, and I'm looking forward to any reply with many thanks!

lizian1611 commented 1 year ago

Hello, I am new to this area, can you give me some advice on how to use FSLSD code for preprocessing and training

Unkrible commented 1 year ago

Hello, I meet the same question. Have you solved it? Which checkpoint do you use in pSp? What code in pSp do you take, encoder.code or encoder.code + pSp.avg_latent

tyrink commented 1 year ago

Hello, I am new to this area, can you give me some advice on how to use FSLSD code for preprocessing and training

Hi, I just follow all the instruction steps released by the author, and I haven't got pleasant results yet.

tyrink commented 1 year ago

Hello, I meet the same question. Have you solved it? Which checkpoint do you use in pSp? What code in pSp do you take, encoder.code or encoder.code + pSp.avg_latent

Hi, I haven't solved it yet. I used 'psp_ffhq_encode.pt' for pSp. And I have tried both encoder.code and encoder.code + pSp.avg_latent, but none of them leads to pleasant visual effects, just as you described in other issue.

Unkrible commented 1 year ago

Hello, although I use ffhq_encode.pt and encoder.code + pSp.avg_latent as described in the author response, the result is still meaningless. Are there other details?

tyrink commented 1 year ago

Hi, I have confirmed the preprocessing steps and tried again, but just got the same meaningless results. And I’m still looking for where I did wrong.